Intelligent control system and method for gas production line

Abstract

The invention relates to an intelligent control system and method for a gas production line. The system comprises a data acquisition module used for acquiring real-time data of gas flow, pressure and components of key nodes of a gas production line; the data processing module is used for primarily processing the real-time data to obtain preprocessed data; the digital twinning module is used for constructing a virtual model consistent with an entity production line on the basis of the preprocessed data, and the virtual model is used for mapping the flowing state of gas in a pipeline, component changes in a separation device and temperature distribution in a heat exchanger in the production process in real time; and the resource scheduling module is used for writing operation data of an actual production line into the virtual model, the operation data is used for simulating different scheduling schemes, calculating a resource allocation result under each scheme according to the different scheduling schemes, and generating a production plan. By adopting the system, the production efficiency can be improved, and the equipment energy consumption and failure rate are reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of gas processing, and particularly relates to an intelligent control system and method for a gas production line. BACKGROUND

[0002] With the rapid development of industrial automation and intelligent manufacturing technology, digitalization and intelligent technology have been gradually introduced into the field of gas production. These technologies realize real-time monitoring and optimal control of the gas production process by integrating various sensors and automatic control systems. However, traditional gas production control systems mainly rely on single sensor data acquisition and simple feedback control, which is difficult to fully reflect the complex production process and dynamic changes.

[0003] In traditional technology, the monitoring and optimization of the gas production process mainly rely on a dispersed sensor network and independent control systems. Although these systems can collect some production data, they lack the ability to deeply analyze and integrate data. The optimization of the production process usually relies on manual experience, and is realized by manually adjusting equipment parameters. In addition, traditional methods also have limitations in resource allocation and production scheduling, and lack effective simulation and verification methods, making it difficult to conduct optimization tests without interfering with actual production.

[0004] The current traditional method has the following problems: the traditional sensor network has a limited coverage range and cannot fully collect key parameters in the gas production process, such as dynamic changes in gas composition, temperature, and pressure; it lacks effective data transmission and processing mechanisms, resulting in insufficient real-time and accuracy of data; the traditional control system cannot realize full-parameter virtual mapping of the production process, making it difficult to reproduce the movement of gas molecules and the details of process switching in a virtual environment. At the same time, in terms of resource allocation and production scheduling, the traditional method cannot effectively simulate the results of different scheduling schemes, making it difficult to optimize resource allocation, resulting in low production efficiency and resource utilization. These problems limit the intelligent level of the gas production process and the improvement of production efficiency. SUMMARY

[0005] Therefore, it is necessary to provide an intelligent control system and method for a gas production line that can improve production efficiency in view of the above technical problems.

[0006] In a first aspect, the application provides an intelligent control system for a gas production line, comprising:

[0007] a data acquisition module for acquiring real-time data of gas flow, pressure and composition of key nodes of the gas production line, the real-time data being acquired in real time by deploying related equipment in the production line;

[0008] a data processing module for preliminarily processing the real-time data to obtain preprocessed data;

[0009] a digital twin module configured to construct a virtual model consistent with the entity production line based on the preprocessed data, the virtual model being used to map in real time a flow state of the gas in the pipeline, a composition change in the separation device, and a temperature distribution in the heat exchanger in the production process;

[0010] a resource scheduling module configured to write running data of the actual production line in the virtual model, the running data being used to simulate different scheduling schemes, to calculate resource allocation results under each scheduling scheme, and to generate a production plan.

[0011] In one of the embodiments, the data acquisition module comprises:

[0012] a gas composition analysis unit configured to obtain gas composition data;

[0013] a temperature detection unit configured to obtain gas temperature data;

[0014] a pressure detection unit configured to obtain gas pressure data;

[0015] a data transmission control unit configured to transmit the gas composition data, the temperature data, and the pressure data to the data processing module to obtain the preprocessed data.

[0016] In one of the embodiments, the digital twin module comprises:

[0017] a data synchronization unit configured to realize data synchronization between the preprocessed data and a digital twin system to obtain real-time synchronization data;

[0018] a dynamic updating unit configured to update the virtual model according to the real-time synchronization data and to map the synchronization data in the dynamically updated virtual model to a virtual environment;

[0019] a visualization unit configured to dynamically display a virtual production process in the mapped virtual environment to a user in a graphical interface, the graphical interface being used for the user to monitor and analyze the production process in real time; the visualization simulates the movement of gas molecules through the following Navier-Stokes equation:

[0020]

[0021] wherein u is the flow rate of the gas, p is the density of the gas, p is the pressure, v is the dynamic viscosity, and f is the external force.

[0022] In one of the embodiments, the dynamic updating unit comprises:

[0023] a pipeline flow state mapping subunit configured to map the flow state of the gas in the pipeline based on the gas flow rate and pressure data, the flow state including the flow rate, the flow direction, and the pressure distribution;

[0024] The separation device component variation mapping subunit is configured to map component variations in the separation device based on the gas component data, the component variations including gas component concentration variations at different separation stages;

[0025] The heat exchanger temperature distribution mapping subunit is configured to map temperature distribution in the heat exchanger based on the temperature data, the temperature distribution including temperature gradient and heat exchange efficiency.

[0026] In one of the embodiments, the resource scheduling module includes:

[0027] The data receiving unit is configured to receive operation data, the operation data including raw material supply amount, market demand data, and equipment operation state parameters;

[0028] The scheduling scheme simulation unit is configured to simulate test and verify different resource allocation scheduling schemes in the virtual model based on the operation data, the scheduling schemes including adjusting compressor operation power and switching separation device combinations;

[0029] The resource allocation calculation unit is configured to calculate resource allocation of each scheduling scheme for different resource allocation scheduling schemes, to obtain corresponding resource allocation results, the resource allocation results being used to indicate the optimized scheduling scheme;

[0030] The production plan generation unit is configured to generate a production plan according to the optimized scheduling scheme, and send the production plan to an actual production line, the production plan being used to control the actual production line to execute gas generation.

[0031] In one of the embodiments, the resource allocation calculation unit includes:

[0032] The optimization objective function result calculation subunit is configured to evaluate the scheduling scheme by the following formula:

[0033]

[0034] wherein C is the optimization objective function result, ω i is the weight of the i-th objective, f i (x) is the function value of the i-th objective, and n is the number of optimization objectives.

[0035] The scheme evaluation subunit is configured to evaluate the pros and cons of each scheduling scheme according to the optimization objective function result, and select the optimized scheduling scheme according to the pros and cons.

[0036] In one of the embodiments, the production plan generation unit includes:

[0037] The instruction conversion subunit is configured to convert the production plan into a control instruction format suitable for an actual production line control terminal, and the control instruction format ensures that the control instruction can be correctly recognized and executed by an actual production line control system.

[0038] The execution monitoring subunit is configured to monitor the execution of the production plan by the actual production line in real time, and collect feedback data in the execution process, the feedback data including equipment operating states, production progress, and abnormal alarm information.

[0039] The feedback adjustment subunit is configured to dynamically adjust the production plan being executed according to the feedback data, and the dynamic adjustment is used to cope with sudden situations or deviations in the actual production process.

[0040] In a second aspect, the present application further provides an intelligent control method of a gas production line, comprising:

[0041] Obtaining real-time data of gas flow, pressure and composition of key nodes of the gas production line, the real-time data being obtained by real-time collection of related equipment deployed in the production line;

[0042] Preliminarily processing the real-time data to obtain preprocessed data;

[0043] Constructing a virtual model consistent with the actual production line based on the preprocessed data, the virtual model being used to real-time map the flow state of the gas in the pipeline, the composition change in the separation device, and the temperature distribution in the heat exchanger in the production process;

[0044] Writing running data of the actual production line into the virtual model, the running data being used to simulate different scheduling schemes, calculating resource allocation results under each scheduling scheme, and generating a production plan.

[0045] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, the memory storing a computer program, and the processor realizing the system for intelligent control of the gas production line according to any of the embodiments of the present application when executing the computer program.

[0046] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program realizes the system for intelligent control of the gas production line according to any of the embodiments of the present application when executed by a processor.

[0047] The intelligent control system and method of the gas production line can realize real-time accurate mapping and intelligent optimization decision of the gas production process by constructing a virtual-real synchronous digital twin system, solve the problems of parameter lag, low energy efficiency and extensive scheduling in the traditional control mode, and significantly improve the operation efficiency, energy utilization rate and decision-making scientificity of the production line. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0049] Figure 1 An implementation environment schematic diagram of the intelligent control system of the gas production line of the present application;

[0050] Figure 2 A structure block diagram of the intelligent control system of the gas production line of the present application;

[0051] Figure 3 A flow chart of the intelligent control method of the gas production line of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0053] The intelligent control system of the gas production line provided by the embodiments of the present application can be applied to, for example Figure 1The production terminal 101 communicates with the server 102 through a network in the illustrated implementation environment. The data storage system can store data required to be processed by the server 102. The data storage system can be integrated on the server 102, or placed on a cloud or other network server. The production terminal 101 can be, but is not limited to, various industrial computers, notebook computers, smart phones, tablet computers and portable wearable devices. The server 102 can be implemented by a stand-alone server or a server cluster composed of multiple servers.

[0054] In combination with the above implementation environment, the application scenarios of the embodiments of the present application are described.

[0055] The embodiments of the present application are applicable to the gas production link of a large chemical plant. By deploying an intelligent control system, the flow, pressure and composition data of the key nodes of the gas production line are collected in real time, and a virtual model is constructed by using digital twin technology for dynamic simulation and optimization scheduling. The system can automatically generate an optimal production plan according to market demand and equipment state, thereby guiding the production of the actual production line gas.

[0056] Only examples are given, and the specific application scenarios are not limited.

[0057] In an exemplary embodiment, as Figure 2 shown, an intelligent control system 10 of a gas production line is provided, which is applied to, for example, a production terminal in Figure 1 , including the following modules 11 to 14. Among them:

[0058] The data acquisition module 11 is used to acquire real-time data of gas flow, pressure and composition of key nodes of the gas production line. The real-time data is collected in real time by deploying related equipment on the production line.

[0059] Exemplarily, the system is applied to an air separation oxygen production line, the outlet flow of the compressor unit, the pressure of the rectification tower and the oxygen purity are collected in real time, and are transmitted to the control center through the industrial Ethernet, thereby providing a raw data basis for subsequent processing. Among them, the key nodes refer to the monitoring points that directly affect the quality of the gas and the stability of the process, including the raw material inlet, the inlet and outlet of the separation tower and the finished product storage tank, etc.; the related equipment includes but is not limited to a gas composition analyzer, a mass flow meter and a laser gas analyzer, etc.

[0060] The data processing module 12 is used to preliminarily process the real-time data to obtain preprocessed data.

[0061] Exemplarily, taking the application of the system to air compressor vibration monitoring as an example, by receiving the original waveform of the vibration sensor, first denoising through low-pass filtering (cut-off frequency 1 kHz), extracting effective characteristic values (such as RMS value 2.8 mm / s), and finally outputting the standardized vibration feature sequence. Real-time data refers to the current / voltage signal directly output by the sensor; preprocessed data is the structured data matrix formed after signal filtering, dimension normalization and outlier removal, with dimensions nxm.

[0062] The digital twin module 13 is used to construct a virtual model consistent with the entity production line based on the preprocessed data, and the virtual model is used to real-time map the flow state of the gas in the pipeline, the composition change in the separation device, and the temperature distribution in the heat exchanger in the production process.

[0063] Specifically, a multi-scale virtual production line including a pipeline CFD (Computational Fluid Dynamics) model, a separation device mass transfer model and a heat exchanger thermodynamic model is constructed by industrial simulation software, the preprocessed data is received in real time to drive the model iteration, the gas flow field, component concentration and temperature distribution are visualized synchronously, and the error rate is controlled within a certain range.

[0064] Taking the air separation device rectification tower as an example, based on the implementation pressure of 0.52 MPa and the temperature of -183℃, the Rayleigh distillation model is used to dynamically predict the top / bottom components (N298.2% / O299.8%), and the deviation from the online chromatograph data is less than 0.05%, thereby realizing the accurate correspondence of "physical parameters→mathematical model→virtual mapping".

[0065] The resource scheduling module 14 is used to write the running data of the actual production line into the virtual model, and the running data is used to simulate different scheduling schemes, calculate the resource allocation results under each scheme according to different scheduling schemes, and generate a production plan.

[0066] Optionally, by injecting the real-time collected production line running data into the digital twin virtual model, a multi-objective optimization engine is constructed based on the reinforcement learning algorithm, a plurality of production scheduling scenarios are simulated in parallel in the virtual environment, the key indicators such as energy efficiency ratio, equipment loss rate and yield under each scheme are calculated by the solver, and finally the Pareto optimal decision algorithm is used to screen out the resource allocation scheme with the highest comprehensive score, a digital production work order containing specific operation parameters and execution timing is automatically generated, and is issued to the field PLC control system for execution through the OPC UA protocol, and the actual execution effect is fed back to the digital twin model to form a closed-loop optimization.

[0067] The virtual model refers to a digital twin model with the same structure and characteristics as the physical production line constructed through computer simulation technology; the operation data of the actual production line refers to the process parameters and operation indexes reflecting the current production state collected from field sensors, control systems and other devices; the scheduling scheme refers to a set of operation strategies including device start-stop, load adjustment and the like formulated for production demand changes; the resource allocation result refers to the optimized values of device operation parameters, energy consumption, raw material ratio and the like resource configuration calculated by the algorithm; and the production plan refers to a production execution scheme including specific operation instructions and time nodes generated according to the optimized result.

[0068] In the above intelligent control system, the modules cooperatively work to form a closed-loop control chain of "perception-processing-simulation-decision", so as to realize rapid response to process changes through digital twin virtual verification without interrupting the actual production, and ensure the stability and economy of the production process.

[0069] In an exemplary embodiment, the data acquisition module comprises the following units:

[0070] A gas composition analysis unit is configured to obtain gas composition data.

[0071] Optionally, a TDLAS tunable laser spectrum analyzer is integrated to scan the gas pipeline in real time, the characteristic absorption spectrum of specific components (such as O2 at 760 nm and N2 at 226 nm) is utilized, the Beer-Lambert law is used to calculate the concentration of each gas, and the data (such as O2 purity 99.6% and CO2 content 200 ppm) are transmitted to the PLC control system through a 4-20 mA analog signal or a Modbus RTU protocol, while a temperature and pressure compensation algorithm is built-in to eliminate the influence of working condition fluctuations, so as to realize continuous online monitoring of gas composition in the production process. The gas composition data refers to the digital measurement results of specific components such as oxygen and nitrogen and their content ratio measured by spectral and chromatographic analysis techniques.

[0072] A temperature detection unit is configured to obtain gas temperature data.

[0073] Optionally, a PT100 platinum resistance temperature sensor is used in combination with a three-wire connection method to eliminate the influence of wire resistance, a constant current source drive and a 24-bit Sigma-Delta type ADC are used for signal acquisition, the Callendar-Van Dusen equation is used to convert the resistance value into a temperature value, a HART protocol communication interface is built-in to realize remote range adjustment and fault self-diagnosis, and the data are uploaded to the DCS system, while an armored stainless steel sheath is used to ensure long-term stable operation in the high-pressure pipeline, thereby providing temperature data meeting the IEC 60751 standard for process control. The gas temperature data refers to physical quantity data in units of Celsius or Kelvin representing the thermal state parameters of the gas.

[0074] a pressure detection unit configured to acquire gas pressure data.

[0075] Optionally, a diffusion silicon piezoresistive pressure transmitter is used to convert the gas pressure into resistance changes of a Wheatstone bridge through an isolation diaphragm, and the signal is conditioned and digitized through a temperature compensation module and a 24-bit high-precision ADC. The original voltage value is converted into a standard pressure value for output using a polynomial fitting algorithm. The gas pressure data refers to the physical quantity data representing the gas mechanical state parameter in units of Pascal or MegaPascal collected by the pressure sensor.

[0076] a data transmission control unit configured to transmit the gas component data, temperature data, and pressure data to a data processing module to obtain preprocessed data.

[0077] Optionally, a timestamp alignment algorithm is used to time-match the heterogeneous data, CRC-32 checksum and outlier filtering are used to ensure data integrity, and the packaged structured data is pushed to the edge computing node at a period of 100 ms using the MQTT protocol. Kalman filtering and feature standardization are completed in the data processing module, and finally the preprocessed data stream with quality identification is generated and transmitted to the cloud digital twin system in real time. The local SD card cache (FAT32 format, 7-day history data is stored in a loop) and 4G wireless backup channel are synchronously supported to ensure that data is not lost when the network is interrupted.

[0078] In one example embodiment, the digital twin module includes the following units:

[0079] a data synchronization unit configured to synchronize the preprocessed data with the digital twin system to obtain real-time synchronized data.

[0080] Specifically, the preprocessed data (including gas flow, pressure, etc.) uploaded by the edge computing node is time-matched using a timestamp alignment algorithm, and only the change data is transmitted to the cloud digital twin system using differential compression technology (compression ratio ≥ 60%). At the same time, a bidirectional heartbeat detection mechanism is used to monitor the network status, and when the synchronization deviation exceeds the threshold (±0.5%), the model parameter calibration is automatically triggered. This data synchronization mechanism ensures that the real-time synchronized data in the virtual model (such as the pipe flow rate 2.1 m / s ± 0.05) is consistent with the physical production line within milliseconds (<200 ms), providing high-fidelity input for subsequent simulation optimization. All synchronization operation records are stored through blockchain, forming an auditable data traceability chain.

[0081] a dynamic updating unit configured to update the virtual model according to the real-time synchronized data, and map the synchronized data in the dynamically updated virtual model to the virtual environment.

[0082] Exemplarily, by calling the API interface of the digital twin engine, a real-time synchronization data stream is received at a cycle of 100 ms, first, a Kalman filter algorithm (process noise covariance Q=0.01, observation noise covariance R=0.1) is used to smooth the input data, then the boundary conditions of the virtual model are dynamically adjusted through the parameter identification module, incremental calculation is performed in the CFD solver, the iterated fluid state (pressure field, velocity field), component concentration distribution and other parameters are written into the time series database, at the same time, the three-dimensional model in the virtual environment is driven to change dynamically through the rendering engine, and the model snapshot with timestamp is generated for version backtracking, finally, millisecond-level synchronization (delay <300 ms) between the physical entity and the virtual environment is realized, when the key parameter deviation (such as pressure difference >0.05 MPa) is monitored, the alarm is automatically triggered and the abnormal event is recorded to the blockchain.

[0083] Among them, the real-time synchronization data refers to the input data stream after time alignment and format unification; the dynamically updated virtual model refers to the latest version of the simulation system after parameter iteration; and the virtual environment refers to the three-dimensional visual interface of the cloud computing platform running the digital twin model.

[0084] The visualization unit is used to dynamically display the virtual production process in the mapped virtual environment to the user in a graphical interface, and the graphical interface is used for the user to monitor and analyze the production process in real time. The visualization simulates the motion of gas molecules by the following Navier-Stokes equation:

[0085]

[0086] Among them, u is the flow rate of the gas, p is the density of the gas, p is the pressure, v is the dynamic viscosity, and f is the external force.

[0087] Optionally, a three-dimensional virtual factory scene is constructed based on a rendering engine, by real-time analyzing the Navier-Stokes equation solution results (including velocity field u, pressure field p, etc.) output by the digital twin system, adopting a particle system to simulate the motion trajectory of gas molecules (10^6 particles per cubic meter are rendered, and the particle velocity vector is synchronized with the simulation data), using Shader programming to realize dynamic coloring (such as displaying the pipeline gradually from blue to red according to the temperature gradient, and when the temperature difference ΔT=50℃, the hue is shifted by 120°), presenting an interactive graphical interface on the Web side through the Three.js library, supporting zooming / rotating / cross-section viewing, integrating real-time data dashboard on the right side of the interface to display key parameters, while providing historical curve comparison and abnormal warning functions, when a red flashing prompt is triggered, the user can perform immersive inspection through a VR headset, the system background uses GPU acceleration to ensure that the rendering frame rate is ≥60 fps at a resolution of 4K, all visualization data is synchronized with the cloud solver, and the system supports exporting working condition snapshots in the standard GlTF format for offline analysis.

[0088] Wherein, the mapped virtual environment refers to a three-dimensional simulation space that has completed real-time data synchronization; the graphical interface refers to a visual monitoring screen containing a data board, a three-dimensional model, and an operation control; the Navier-Stokes equation is a partial differential equation set describing the momentum conservation of viscous fluid; the gas flow rate u is the volume flow rate of fluid micro-particles per unit time through a unit area; the gas density p is the mass of fluid per unit volume; the pressure p is the force per unit area vertically exerted by the fluid; the dynamic viscosity m is a physical parameter reflecting the viscous characteristics of the fluid; and the external force f includes volume forces such as gravity and electromagnetic force.

[0089] In the intelligent control system of the above gas production line, the data synchronization unit ensures consistency of virtual and real data, and the visualization unit provides interactive analysis tools, so that process adjustment schemes can be preformed in the virtual environment, the production abnormality identification speed is improved, and the decision response time is shortened.

[0090] In one of the embodiments, an intelligent control system of a gas production line is provided, and the dynamic updating unit includes the following sub-units:

[0091] A pipeline flow state mapping sub-unit is configured to map the flow state of the gas in the pipeline based on the gas flow and pressure data, and the flow state includes flow rate, flow direction, and pressure distribution.

[0092] Optionally, the original data of the gas flow meter and the pressure transmitter are analyzed in real time, the simplified Navier-Stokes equation is solved by using the finite volume method, and the flow rate field (0.5-20 m / s range) and the pressure gradient are calculated on a two-dimensional pipeline grid A dynamic streamline diagram and a color pressure cloud diagram are generated by using a rendering engine, flow direction arrows and key parameter labels are superimposed and displayed, data is pushed to a visualization interface, touch screen interaction is supported to adjust display parameters, and an alarm is automatically triggered and an event log is recorded when a flow abnormality is detected. Wherein, the gas flow data is the volume or mass of the gas passing through the pipeline cross section per unit time measured by the flow meter; the pressure data is the force intensity of the gas in the pipeline acting on the pipe wall collected by the pressure sensor; the flow state is the dynamic characteristics of the gas in the pipeline conveying process; the flow rate is the movement rate of the gas micro-particles in the axial direction of the pipeline, the flow direction is the vector direction of the gas flow; and the pressure distribution is the pressure gradient change of each cross section position of the pipeline.

[0093] A separation device component change mapping sub-unit is configured to map the component change in the separation device based on the gas component data, and the component change includes the concentration change of the gas components at different separation stages.

[0094] Optionally, the component data of the laser gas analyzer is acquired in real time through a high-speed data acquisition card, combined with the temperature and pressure parameters of the rectifying column, a component transfer model is established by using the Fick diffusion law and the phase equilibrium equation, the concentration field distribution is solved in a three-dimensional grid space, dynamic rendering is realized through shader programming, the concentration curve and the three-dimensional concentration cloud chart of the tray stage are displayed in layers on the HMI interface, and when a component deviation is detected, the abnormal area is automatically marked and the historical data is traced back (compared with the trend in the previous 10 minutes), and the entire calculation process realizes real-time visualization update of 15 frames per second. The gas component data is the volume fraction or molar fraction of each gas component measured by the online analyzer; the separation device is a process equipment for separating the components of a gas mixture; and the different separation stages refer to spatial regions such as the feeding section, the rectifying section, and the stripping section of the separation device.

[0095] The heat exchanger temperature distribution mapping subunit is configured to map a temperature distribution in the heat exchanger based on the temperature data, the temperature distribution including a temperature gradient and a heat exchange efficiency.

[0096] Optionally, the tube side / shell side temperature data is collected by a distributed temperature sensor array, a three-dimensional unsteady heat conduction equation is solved by using the finite element method, and the temperature field distribution is calculated, a thermodynamic map is generated in real time and the maximum temperature difference area is marked, the heat transfer coefficient K value and the efficiency ε-NTU are calculated synchronously, an interactive 3D temperature cloud chart is presented through an industrial VR head-mounted display (supporting gesture rotation and zooming), and when local overheating (> set value 10℃ for 30s) is detected, an alarm is automatically triggered and a thermal resistance distribution report is generated, the data is updated to the MES system through a 5G private network every 5 seconds, and the edge node performs scaling prediction to guide cleaning cycle optimization.

[0097] The temperature data is a medium temperature measurement value collected by a thermocouple or a thermal resistance sensor; the heat exchanger is a process equipment for realizing heat exchange between cold and hot fluids; and the temperature distribution is a three-dimensional feature of the temperature field at each spatial position inside the heat exchanger.

[0098] In the above intelligent mapping unit, the three mapping subunits respectively construct high-fidelity virtual mapping from the dimensions of fluid motion, component separation, and energy transfer, realize early prediction of process deviation through multi-physical field coupling visualization, and thus guide optimization of the control strategy to reduce energy consumption.

[0099] In one of the embodiments, an intelligent control system of a gas production line is provided, and the resource scheduling module includes the following units:

[0100] The data receiving unit is configured to receive operation data, the operation data including raw material supply amount, market demand data, and equipment operation state parameters.

[0101] Preferably, the device state parameters in the production line PLC are collected in real time, the raw material supply plan and market demand data in XML format are obtained by interfacing the ERP system API, the heterogeneous data is uniformly stored in a time series database, abnormal inputs are filtered through a data verification module, and finally a structured data package containing data quality labels (0-100% reliability score) is generated, which is pushed to the digital twin system every 5 seconds through a Kafka message queue, and local caching is enabled in the event of network interruption, ensuring effective control of the timeliness of production scheduling data. The raw material supply quantity is the amount of raw materials input into the production process per unit time; the market demand data is external input information such as order demand and delivery period from the sales system; the device running state parameters are physical quantities such as compressor speed and valve opening that directly represent the working state of the machine.

[0102] The scheduling scheme simulation unit is configured to simulate and verify different resource allocation scheduling schemes in the virtual model based on the operation data, the scheduling schemes including adjusting the compressor operating power and switching the combination of separation devices.

[0103] Specifically, the API interface of the digital twin engine is called to obtain production line operation data in real time, and multi-threaded simulation is started in parallel in a virtual environment (each scheme runs independently in a container), a mixed integer programming algorithm is used to generate a set of resource allocation strategies, a computational fluid dynamics solver is used to simulate the adjusted gas flow distribution and component changes, and a reinforcement learning model is used to evaluate the overall energy efficiency ratio of each scheme, and finally a set of optimal solutions is output and the changes in pressure field and concentration field are displayed through a three-dimensional visualization interface. When the simulation results deviate from the actual data by more than 5%, the model parameter calibration is automatically triggered, and all simulation data (including intermediate iteration process) are stored in a blockchain to ensure auditability. Simulation testing is a process of numerical simulation and verification of strategies without affecting actual production; resource allocation is an optimized configuration scheme for production equipment, energy, raw materials, etc.; and the scheduling scheme is a set of device operation instructions formulated to meet production needs.

[0104] The resource allocation calculation unit is configured to calculate the resource allocation of each scheduling scheme for different resource allocation scheduling schemes, and obtain corresponding resource allocation results, which are used to indicate the acquisition of the optimal scheduling scheme.

[0105] Optionally, by establishing a multi-objective optimization model, 20-30 candidate scheduling schemes are calculated in parallel by using an improved NSGA-III algorithm, and the iteration optimization of the whole scheme set is completed every 5 minutes. The calculation process calls the device parameters, energy prices and other constraint conditions in the digital twin database in real time, outputs the three-dimensional evaluation indexes and Pareto frontier solution set of each scheme, selects the optimal scheme with a comprehensive score > 0.85 through the TOPSIS decision-making method, and sends the calculation results to the PLC for execution. At the same time, a decision-making report containing key KPI comparison column chart and energy saving prediction is generated, and all intermediate data is stored in the time series database for post-analysis. When the actual running index deviates from the predicted value by ± 5%, automatic re-optimization is triggered. Among them, the resource allocation result is obtained by calculating the quantitative index set of device utilization rate, energy consumption distribution, raw material consumption, etc.; the optimal scheduling scheme refers to the execution strategy with the best comprehensive performance selected after multi-objective trade-off.

[0106] A production plan generation unit is configured to generate a production plan according to the optimal scheduling scheme and send the production plan to an actual production line. The production plan is used to control the actual production line to execute gas generation.

[0107] Among them, by analyzing the instruction set output by the optimal scheduling scheme, a standardized process control sequence is generated using an industrial automation markup language, and the instruction package is sent to the on-site PLC control system. At the same time, an electronic work order containing quality inspection points and equipment inspection items is automatically generated and pushed to the operation terminal. In the production execution process, the deviation between the actual parameters and the planned target value is compared in real time. When the deviation exceeds the tolerance for three consecutive sampling periods, dynamic rescheduling is triggered. All execution records are stored through blockchain and the production progress state of the digital twin model is updated synchronously. The actual production line refers to an entity production system composed of physical devices such as compressors and separation devices; gas generation refers to the production process of converting raw gas into target products through separation and purification processes.

[0108] In the above intelligent production scheduling system, a "data-driven-virtual optimization-decision execution" intelligent closed loop is formed through consecutive functional units, realizing the whole process processing from process abnormality detection to optimal scheme landing in a short time.

[0109] In one example embodiment, an intelligent control system for a gas production line is provided, and the resource allocation calculation unit includes the following sub-units:

[0110] An optimal objective function result calculation sub-unit is configured to evaluate the scheduling scheme by the following formula:

[0111]

[0112] Among them, C is the optimal objective function result, ω i is the weight of the i-th objective, and fi (x) is the function value of the i-th objective, and n is the number of optimization objectives;

[0113] Furthermore, by calling the real-time operation data in the digital twin database, a dynamic weight allocation algorithm is used to determine the weights of each target (energy consumption α1 = 0.4, output α2 = 0.3, equipment loss α3 = 0.3), and the normalized objective function values ​​(f1 energy consumption index is standardized to the [0,1] interval through Min-Max, f2 output index is converted according to the compliance rate, etc.) are weighted summed (C = Σα i f i , i = 1 to n), completes the evaluation and ranking of 100 solutions in 5ms using GPU acceleration. The output includes a 3D radar chart and a comprehensive score list. When a weight conflict with the current production strategy is detected, the expert system is automatically triggered to recalibrate the weights. All calculation results are stored on the blockchain and synchronized to the decision dashboard in real time, allowing operators to manually adjust the weights and immediately regenerate the ranking. The optimization objective function result C is the comprehensive evaluation score of the solution obtained through weighted calculation.

[0114] The scheme evaluation subunit is used to evaluate the pros and cons of each scheduling scheme based on the results of the optimization objective function, and select the optimized scheduling scheme based on the pros and cons.

[0115] Optionally, by receiving the scoring matrix of each scheme output by the calculation subunit of the optimization objective function result, a multi-criteria decision-making method is used to filter the feasibility of the schemes in combination with production constraints, and a ranked list of schemes is generated in real time. The distribution of the frontiers of each scheme is displayed through a three-dimensional visualization interface. When the optimal scheme proximity C_i>0.9, it is automatically marked as a recommended scheme. At the same time, manual intervention is supported to adjust the preferred weight. Finally, a decision report with risk identification is output, and the scheme is ensured to be tamper-proof through digital signature. All evaluation process data is stored in a time series database for audit backtracking, ensuring a complete traceability chain from algorithm decision-making to actual implementation. The pros and cons refer to the relative ranking results of the schemes based on KPIs such as energy efficiency and output.

[0116] In the above-mentioned intelligent optimization decision-making system, through the decision-making closed loop of "quantitative scoring-intelligent optimization", it is possible to balance conflicting goals such as energy consumption, output, and equipment loss, and improve the comprehensive benefit indicators of the production plan.

[0117] In an exemplary embodiment, an intelligent control system for a gas production line is provided, wherein a production plan generating unit includes the following subunits:

[0118] The instruction conversion subunit is used to convert the production plan into a control instruction format that is suitable for the actual production line control terminal. The control instruction format ensures that the control instruction can be correctly identified and executed by the actual production line control system;

[0119] Exemplarily, by parsing the production plan in JSON format (containing device ID, target parameter value and execution timestamp), calling the preset PLC instruction template library, converting the high-level process instruction into a structured text program block conforming to the IEC 61131-3 standard, adding CRC-16 check code and timing mark, issuing to the field PLC and monitoring the instruction execution state in real time, automatically triggering the retransmission mechanism when detecting that the instruction is not executed on time (timeout > 500 ms), all conversion records (including the mapping relationship between the original plan and the generated instruction) are stored through the blockchain, ensuring the end-to-end traceability from virtual decision to physical execution, while supporting the pre-compilation of instructions in offline mode and adapting to the protocol differences of different brands of controllers. The actual production line control terminal refers to the field industrial control system such as PLC and DCS; the control instruction format refers to the industrial programming language specification such as structured text (ST) and ladder diagram (LD) conforming to the IEC 61131-3 standard; the control instruction refers to the digital command directly driving the action of the actuator; and the actual production line control system refers to the automation execution system composed of the controller, I / O module and communication network.

[0120] The execution monitoring subunit is configured to monitor the execution of the production plan by the actual production line in real time and collect feedback data in the execution process, the feedback data including device running state, production progress and abnormal alarm information.

[0121] Optionally, the PLC register data is collected in real time by the industrial Internet of Things edge node with a sampling period of 100 ms, the MES system work order state is scanned, and the OPC UA alarm event is listened to, the execution deviation (such as production progress lag ≥ 8%) is detected by using a sliding time window algorithm, the structured feedback data (in JSON format, including timestamp, device ID, parameter value and quality code) is pushed to the digital twin system through a real-time stream processing engine, and the execution heat map is dynamically displayed on the human-computer interface, the sound and light alarm is triggered immediately when a key abnormality is identified, and a fault diagnosis report is automatically generated, all monitoring data is written into a time series database and synchronized to the blockchain, and warning information is pushed to the mobile terminal, forming a closed-loop monitoring network from instruction issuance to execution feedback. The execution state is the actual response state of the control instruction in the production field; and the feedback data is a real-time monitoring data set reflecting the production execution effect.

[0122] The feedback adjustment subunit is configured to dynamically adjust the production plan being executed according to the feedback data, and the dynamic adjustment is used to cope with the sudden situation or deviation in the actual production process.

[0123] Further, by comparing the predicted values of the digital twin system with the on-site sensor feedback data in real time, a model predictive control algorithm is used to generate adjustment strategies every 30 seconds, the corrected parameters are dynamically written into the PLC control program, and the key constraint conditions are monitored. When a sudden raw material interruption is detected, it automatically switches to an emergency production mode. All adjustment records are stored through blockchain and trigger the digital twin model to update synchronously. The man-machine collaborative interface during adjustment allows operators to manually override automatic decisions within a range of ±15%, ensuring that the process is stable while achieving minute-level dynamic optimization response. Dynamic adjustment refers to online optimization and modification of production parameters according to real-time working condition changes; sudden situation refers to unexpected abnormal events such as equipment failure and raw material fluctuations; and deviation refers to the difference between actual running parameters and planned target values.

[0124] In the above intelligent closed-loop control system, through the intelligent closed loop of "instruction conversion - execution tracking - dynamic adjustment", the process flow can be optimized in real time without interrupting production, reducing abnormal downtime and improving raw material utilization.

[0125] To further illustrate the scheme of the embodiments of the present application, a specific example is described below.

[0126] The embodiment provides an air separation oxygen production line system and method. The system realizes real-time monitoring and optimization control of the production process through digital twin technology.

[0127] High-precision sensor networks are deployed at key nodes such as the outlet of the compressor and the inlet and outlet of the rectification tower in the air separation oxygen production line. TDLAS laser gas analyzers monitor the oxygen and nitrogen concentrations in real time, with a measurement accuracy of 0.1%. PT100 temperature sensors detect the process gas temperature, with a range of -200°C to +500°C. Piezoresistive pressure transducers measure pipeline pressure, with a range of 0-10 MPa. These sensors collect data at a cycle of 100 milliseconds and transmit them to edge computing nodes through a 5G network.

[0128] The edge computing nodes preprocess the raw data. Kalman filtering algorithm is used to eliminate signal noise, and Z-score method is used to normalize parameters of different dimensions. The preprocessed data is pushed to the cloud digital twin system.

[0129] The digital twin system constructs a three-dimensional virtual production line model. Among them, the pipeline fluid model calculates the gas flow rate distribution based on the Navier-Stokes equation, the rectification tower model predicts the component change using the Rayleigh distillation equation, and the heat exchanger model simulates the temperature field through the Fourier heat conduction law. The model grid accuracy reaches 1 cubic centimeter, and the time step is set to 0.1 seconds, which can accurately reproduce the actual production process.

[0130] When the production plan needs to be adjusted, the system conducts simulation tests in the virtual environment. For example, in response to changes in market demand, the system simulates three scheduling schemes: scheme A increases the power of the air compressor from 110 kW to 120 kW, which is expected to increase production by 8%; scheme B activates the standby adsorption tower, which is expected to reduce energy consumption by 5%; and scheme C adjusts the reflux ratio of the rectification tower, which is expected to increase the purity of oxygen by 0.2%. Through multi-objective optimization algorithm evaluation, the scheme with the highest comprehensive score is selected for implementation.

[0131] The system converts the optimized production plan into PLC executable instructions. The instructions contain specific device operation parameters and execution timing, such as "increase the air compressor frequency to 45 Hz at T0, and adjust the reflux valve opening to 65% at T0+30 seconds". These instructions are issued to the field control system through industrial Ethernet.

[0132] During execution, the system monitors actual production data in real time. When the rectification tower pressure fluctuation is detected to exceed 0.05 MPa, the dynamic adjustment mechanism is automatically triggered, and the operation parameters are fine-tuned through the model predictive control algorithm to ensure the stability of the production process. All operation records and adjustment history are stored in the time series database, supporting post-analysis and traceability.

[0133] Based on the same inventive concept, the embodiments of the present application also provide a method for intelligent control of a gas production line. The implementation scheme for solving the problem provided by the method is similar to the implementation scheme described in the above system, so the specific limitations in one or more embodiments of the method for intelligent control of a gas production line provided below can refer to the limitations of the intelligent control system of a gas production line described above, and will not be described here.

[0134] In an exemplary embodiment, as shown in Figure 3 a method for intelligent control of a gas production line is provided, comprising:

[0135] S111, acquiring real-time data of gas flow, pressure and composition of key nodes of the gas production line, the real-time data being obtained by real-time collection of related devices deployed in the production line;

[0136] S112, preliminarily processing the real-time data to obtain preprocessed data;

[0137] S113, constructing a virtual model consistent with the entity production line based on the preprocessed data, the virtual model being used to real-time map the flow state of gas in the pipeline, the composition change in the separation device and the temperature distribution in the heat exchanger in the production process;

[0138] S114, writing running data of the actual production line in the virtual model, the running data being used to simulate different scheduling schemes, calculating resource allocation results under each scheme according to different scheduling schemes, and generating a production plan.

[0139] In one embodiment, real-time data of gas flow, pressure and composition of key nodes of the gas production line are obtained, and the real-time data are obtained by real-time collection of related equipment deployed in the production line, including:

[0140] S211, obtaining gas composition data;

[0141] S212, obtaining gas temperature data;

[0142] S213, obtaining gas pressure data;

[0143] S214, transmitting the gas composition data, temperature data and pressure data to a data processing module to obtain preprocessed data.

[0144] In one embodiment, a virtual model consistent with the entity production line is constructed based on the preprocessed data, including:

[0145] S311, realizing data synchronization of the preprocessed data and the digital twin system to obtain real-time synchronization data;

[0146] S312, updating the virtual model according to the real-time synchronization data, and mapping the synchronization data in the dynamically updated virtual model to a virtual environment;

[0147] S313, dynamically displaying the virtual production process in the mapped virtual environment to the user in a graphical interface, and the graphical interface is used for real-time monitoring and analysis of the production process by the user; visualization simulates the motion of gas molecules through the following Navier-Stokes equation:

[0148]

[0149] Wherein, u is the gas flow rate, p is the gas density, p is the pressure, v is the dynamic viscosity, and f is the external force.

[0150] In one embodiment, the virtual model is updated according to the real-time synchronization data, and the synchronization data in the dynamically updated virtual model is mapped to a virtual environment, including:

[0151] S411, mapping the flow state of the gas in the pipeline based on the gas flow and pressure data, the flow state including flow rate, flow direction and pressure distribution;

[0152] S412, mapping the composition change in the separation device based on the gas composition data, the composition change including the concentration change of the gas composition in different separation stages;

[0153] S413, mapping the temperature distribution in the heat exchanger based on the temperature data, the temperature distribution including temperature gradient and heat exchange efficiency.

[0154] In one of the embodiments, the running data of the actual production line is written in the virtual model, the running data is used to simulate different scheduling schemes, the resource allocation results under each scheme are calculated according to the different scheduling schemes, and the production plan is generated, including:

[0155] S511, receiving running data, the running data including raw material supply amount, market demand data and equipment running state parameters;

[0156] S512, simulating and verifying different resource allocation scheduling schemes in the virtual model based on the running data, the scheduling schemes including adjusting the running power of the compressor and switching the combination of the separation device;

[0157] S513, calculating the resource allocation of each scheduling scheme for different resource allocation scheduling schemes, obtaining the corresponding resource allocation results, the resource allocation results being used to indicate the acquisition of the optimized scheduling scheme;

[0158] S514, generating the production plan according to the optimized scheduling scheme, and sending the production plan to the actual production line, the production plan being used to control the actual production line to execute the gas generation.

[0159] In one of the embodiments, the resource allocation of each scheduling scheme is calculated for different resource allocation scheduling schemes, and the corresponding resource allocation results are obtained, including:

[0160] S611, evaluating the scheduling scheme by the following formula:

[0161]

[0162] Wherein, C is the optimization objective function result, ω i is the weight of the i-th objective, f i (x) is the function value of the i-th objective, and n is the number of optimization objectives;

[0163] S612, evaluating the pros and cons of each scheduling scheme according to the optimization objective function result, and selecting the optimized scheduling scheme according to the pros and cons.

[0164] In one of the embodiments, the production plan is generated according to the optimized scheduling scheme, and the production plan is sent to the actual production line, including:

[0165] S711, converting the production plan into a control instruction format suitable for the actual production line control terminal, the control instruction format ensuring that the control instruction can be correctly recognized and executed by the actual production line control system;

[0166] S712, monitoring the execution of the production plan by the actual production line in real time, and collecting feedback data in the execution process, the feedback data including equipment running state, production progress and abnormal alarm information;

[0167] S713, according to the feedback data, dynamically adjusting the production plan being executed, dynamically adjusting for coping with the actual production process or deviation.

[0168] It should be understood that although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0169] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the modules of the intelligent control system of the gas production line as described above when executing the computer program.

[0170] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the modules in the above system embodiments.

[0171] For the device embodiment, since it basically corresponds to the system embodiment, the relevant part is described in the part of the system embodiment. The above described device embodiment is only schematic, wherein the components described as separate components can or can not be physically separated, and the components displayed as a unit can or can not be a physical unit, i.e. can be located in one place, or can be distributed to multiple network units. According to the actual needs, part or all of the modules can be selected to achieve the purpose of the present disclosure. Those skilled in the art can understand and implement without creative labor.

[0172] The above described embodiments only express several implementation manners of the present application, which are described in detail and specifically, but should not be understood as the limitation of the patent scope of the application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which are all within the protection scope of the present application.

Claims

1. An intelligent control system for a gas production line, characterized in that: The system comprises: The data acquisition module is used to obtain real-time data on gas flow, pressure, and composition at key nodes of the gas production line. The real-time data is collected in real time by relevant equipment deployed on the production line; A data processing module, used for performing preliminary processing on the real-time data to obtain preprocessed data; A digital twin module is used to build a virtual model consistent with the physical production line based on the preprocessed data, and the virtual model is used to map in real time the flow state of gas in the pipeline, the composition changes in the separation device, and the temperature distribution in the heat exchanger during the production process; The resource scheduling module is used to write the operating data of the actual production line into the virtual model. The operating data is used to simulate different scheduling schemes, calculate the resource allocation results under each scheme according to the different scheduling schemes, and generate a production plan.

2. The system according to claim 1, wherein: The data acquisition module includes: A gas composition analysis unit, used to obtain gas composition data; A temperature detection unit, used to obtain gas temperature data; A pressure detection unit, used to obtain gas pressure data; The data transmission control unit is used to transmit the gas composition data, temperature data and pressure data to the data processing module to obtain pre-processed data.

3. The system according to claim 1, wherein: The digital twin module includes: A data synchronization unit, configured to synchronize the preprocessed data with the data of the digital twin system to obtain real-time synchronized data; A dynamic updating unit, configured to update the virtual model according to the real-time synchronization data, and map the synchronization data in the dynamically updated virtual model to the virtual environment; A visualization unit is used to dynamically display the mapped virtual production process in the virtual environment to the user using a graphical interface, which is used for the user to monitor and analyze the production process in real time; the visualization simulates the movement of gas molecules through the following Navier-Stokes equations: Where u is the gas flow rate, ρ is the gas density, p is the pressure, υ is the dynamic viscosity, and f is the external force.

4. The system according to claim 3, characterized in that The dynamic update unit includes: a pipeline flow state mapping subunit, configured to map the flow state of the gas in the pipeline based on the gas flow and pressure data, wherein the flow state includes flow velocity, flow direction, and pressure distribution; a separation device composition change mapping subunit, configured to map composition changes in the separation device based on the gas composition data, wherein the composition changes include changes in gas component concentrations at different separation stages; The heat exchanger temperature distribution mapping subunit is used to map the temperature distribution in the heat exchanger based on the temperature data, where the temperature distribution includes a temperature gradient and a heat exchange efficiency.

5. The system according to claim 1, wherein: The resource scheduling module includes: a data receiving unit, configured to receive the operating data, wherein the operating data includes raw material supply, market demand data, and equipment operating status parameters; a scheduling scheme simulation unit, configured to simulate, test, and verify, in the virtual model, the scheduling schemes for different resource allocations based on the operating data, the scheduling schemes including adjusting compressor operating power and switching separation device combinations; a resource allocation calculation unit, configured to calculate the resource allocation of each scheduling scheme for the different resource allocations, and obtain a corresponding resource allocation result, wherein the resource allocation result is used to indicate the acquisition of an optimized scheduling scheme; A production plan generating unit is used to generate a production plan according to the optimized scheduling plan and send the production plan to the actual production line, wherein the production plan is used to control the actual production line to execute gas generation.

6. The system according to claim 5, characterized in that The resource allocation calculation unit includes: The optimization objective function result calculation subunit is used to evaluate the scheduling solution using the following formula: Among them, C is the result of the optimization objective function, ω i is the weight of the i-th target, f i (x) is the function value of the i-th objective, and n is the number of optimization objectives; The scheme evaluation subunit is used to evaluate the pros and cons of each scheduling scheme according to the result of the optimization objective function, and select the optimized scheduling scheme according to the pros and cons.

7. The system according to claim 5, characterized in that The production plan generating unit includes: An instruction conversion subunit, configured to convert the production plan into a control instruction format adapted to the actual production line control terminal, wherein the control instruction format ensures that the control instruction can be correctly identified and executed by the actual production line control system; An execution monitoring subunit, configured to monitor in real time the execution of the production plan by the actual production line and collect feedback data during the execution process, the feedback data including equipment operating status, production progress, and abnormal alarm information; The feedback adjustment subunit is used to dynamically adjust the production plan being executed based on the feedback data, and the dynamic adjustment is used to deal with emergencies or deviations in the actual production process.

8. An intelligent control method for a gas production line, characterized in that: The method comprises: Obtain real-time data on gas flow, pressure, and composition at key nodes of the gas production line. The real-time data is collected in real time by relevant equipment deployed on the production line. Performing preliminary processing on the real-time data to obtain preprocessed data; Building a virtual model consistent with the physical production line based on the preprocessed data, the virtual model is used to map the flow state of gas in the pipeline, the composition changes in the separation device, and the temperature distribution in the heat exchanger in real time during the production process; The operation data of the actual production line is written into the virtual model. The operation data is used to simulate different scheduling schemes. The resource allocation results under each scheme are calculated according to the different scheduling schemes to generate a production plan.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the system according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the system according to any one of claims 1 to 7 are implemented.

Images